© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 49981
    Prev
    Next
    INDEX
    Explanations

    look, bending, pulling, speak

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĸ²
    -0.09
    ç´¯
    -0.09
    æ¯ı天
    -0.08
    åĿı
    -0.08
    Ø´ÙĪر
    -0.08
    壮
    -0.08
    kowski
    -0.08
    æĺŃ
    -0.08
    æĢķ
    -0.08
    æıIJåĢ¡
    -0.08
    POSITIVE LOGITS
    çĮĽ
    0.10
    å¥ĭåĬĽ
    0.09
     QByteArray
    0.09
    è¿Īè¿Ľ
    0.09
    çĶ¨åĬĽ
    0.09
    å°½åĬĽ
    0.09
    éĢĤ
    0.09
    oky
    0.09
     inh
    0.09
    åī§
    0.09
    Activations Density 0.059%

    No Known Activations